{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FMR6TAKPY4GK7B2J6PENHAJL7N","short_pith_number":"pith:FMR6TAKP","canonical_record":{"source":{"id":"2110.04627","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-09T18:36:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7b3bfcc264af0f8477ff69f4872107cbe3567a6ffb64ac00190bf727d3d480c","abstract_canon_sha256":"1281174dc868bc9ba29a7618a8026ba8d4e9294520a78257df36a7f3417a8909"},"schema_version":"1.0"},"canonical_sha256":"2b23e9814fc70caf8749f3c8d3812bfb427c20561b0eb78e59e0f5adcfb00686","source":{"kind":"arxiv","id":"2110.04627","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04627","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04627v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04627","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"FMR6TAKPY4GK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FMR6TAKPY4GK7B2J","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FMR6TAKP","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FMR6TAKPY4GK7B2J6PENHAJL7N","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04627","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-09T18:36:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7b3bfcc264af0f8477ff69f4872107cbe3567a6ffb64ac00190bf727d3d480c","abstract_canon_sha256":"1281174dc868bc9ba29a7618a8026ba8d4e9294520a78257df36a7f3417a8909"},"schema_version":"1.0"},"canonical_sha256":"2b23e9814fc70caf8749f3c8d3812bfb427c20561b0eb78e59e0f5adcfb00686","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.953492Z","signature_b64":"3v/dICYmc+w1JF4DUHwwfybQw4G3iJkbUnOd6djYbfNMvhtQtP6pJjrs1wRO+hBEWqijG4GR8yj1tBDBQMeMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b23e9814fc70caf8749f3c8d3812bfb427c20561b0eb78e59e0f5adcfb00686","last_reissued_at":"2026-05-17T23:38:46.953044Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.953044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04627","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ILI8mlE4PkeESepC1Lg1fBuse+uQedo6c99oidT01DCSn7bTLRRPAS/D9vO9jKTp8ppAUClb9kueUO/3b9FCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T05:09:59.762278Z"},"content_sha256":"c7e05c11cb65642eea53d4c7eec2fc421bd37c71f01913ae581d68be3327684b","schema_version":"1.0","event_id":"sha256:c7e05c11cb65642eea53d4c7eec2fc421bd37c71f01913ae581d68be3327684b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FMR6TAKPY4GK7B2J6PENHAJL7N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vector-quantized Image Modeling with Improved VQGAN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An improved ViT-VQGAN produces discrete image tokens that let an autoregressive Transformer reach an Inception Score of 175.1 and FID of 4.17 on ImageNet.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Ku, Han Zhang, James Qin, Jason Baldridge, Jiahui Yu, Jing Yu Koh, Ruoming Pang, Xin Li, Yonghui Wu, Yuanzhong Xu","submitted_at":"2021-10-09T18:36:00Z","abstract_excerpt":"Pretraining language models with next-token prediction on massive text corpora has delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both generative and discriminative language tasks. Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively. The discrete image tokens are encoded from a learned Vision-Transformer-based VQGAN (ViT-VQGAN). We first propose multiple improvements over vanilla VQGAN from architecture to codebook learnin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When trained on ImageNet at 256×256 resolution, we achieve Inception Score (IS) of 175.1 and Fréchet Inception Distance (FID) of 4.17, a dramatic improvement over the vanilla VQGAN, which obtains 70.6 and 17.04 for IS and FID, respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the discrete tokens produced by the improved ViT-VQGAN retain enough visual information for autoregressive modeling to succeed at both high-quality generation and strong unsupervised representations without critical loss of detail or mode collapse.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An improved ViT-VQGAN produces discrete image tokens that let an autoregressive Transformer reach an Inception Score of 175.1 and FID of 4.17 on ImageNet.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b4daf46dd03dca15b66d07073bf100f3c56513e2ce4f99fd67b364bc3e1ab25b"},"source":{"id":"2110.04627","kind":"arxiv","version":3},"verdict":{"id":"68ed06e5-14f0-41ec-ba4d-07d5e8bc5c83","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T18:36:26.666226Z","strongest_claim":"When trained on ImageNet at 256×256 resolution, we achieve Inception Score (IS) of 175.1 and Fréchet Inception Distance (FID) of 4.17, a dramatic improvement over the vanilla VQGAN, which obtains 70.6 and 17.04 for IS and FID, respectively.","one_line_summary":"Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the discrete tokens produced by the improved ViT-VQGAN retain enough visual information for autoregressive modeling to succeed at both high-quality generation and strong unsupervised representations without critical loss of detail or mode collapse.","pith_extraction_headline":"An improved ViT-VQGAN produces discrete image tokens that let an autoregressive Transformer reach an Inception Score of 175.1 and FID of 4.17 on ImageNet."},"references":{"count":75,"sample":[{"doi":"","year":2010,"title":"Schwing, Jan Kautz, and Arash Vahdat","work_id":"0fe7dc60-401a-4c98-a434-f44dc197d8f0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1906,"title":"Learning representations by maximizing mutual information across views","work_id":"65bca3d5-78f4-42d4-a6b1-cec1b702a646","ref_index":2,"cited_arxiv_id":"1906.00910","is_internal_anchor":true},{"doi":"","year":2020,"title":"Towards causal benchmarking of bias in face analysis algorithms, 2020","work_id":"6501ce5d-4889-498d-9bfe-6701c3b26b5b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"BEiT: BERT Pre-Training of Image Transformers","work_id":"d74eda3c-bf7e-45f1-a8f1-a0137ecca3f4","ref_index":4,"cited_arxiv_id":"2106.08254","is_internal_anchor":true},{"doi":"","year":2019,"title":"Large scale gan training for high fidelity natural image synthesis","work_id":"c8a7029d-c609-4cc5-8c21-654c100ca506","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":75,"snapshot_sha256":"35425ef17774a3871e1cc345ffc0fd40dfeb6c986012deae26f725c5ac88b615","internal_anchors":14},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0eec636ccc08a7e63b3e7b5fb0dd1306cee67f0d27686e029740c6322eb95b4e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"68ed06e5-14f0-41ec-ba4d-07d5e8bc5c83"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKRxnAqvSubLN27AEYXujY35WRPzSbxtLZOqkefmaN/eZzOGyp1FBxcp2G6jTtrzDi84znVAbtz6190UkR7OCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T05:09:59.762964Z"},"content_sha256":"e490304196f7f5212ad35a3b6733e12adadea75c1e84dda2c4a2a830ac10614d","schema_version":"1.0","event_id":"sha256:e490304196f7f5212ad35a3b6733e12adadea75c1e84dda2c4a2a830ac10614d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMR6TAKPY4GK7B2J6PENHAJL7N/bundle.json","state_url":"https://pith.science/pith/FMR6TAKPY4GK7B2J6PENHAJL7N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMR6TAKPY4GK7B2J6PENHAJL7N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T05:09:59Z","links":{"resolver":"https://pith.science/pith/FMR6TAKPY4GK7B2J6PENHAJL7N","bundle":"https://pith.science/pith/FMR6TAKPY4GK7B2J6PENHAJL7N/bundle.json","state":"https://pith.science/pith/FMR6TAKPY4GK7B2J6PENHAJL7N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMR6TAKPY4GK7B2J6PENHAJL7N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FMR6TAKPY4GK7B2J6PENHAJL7N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1281174dc868bc9ba29a7618a8026ba8d4e9294520a78257df36a7f3417a8909","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-09T18:36:00Z","title_canon_sha256":"a7b3bfcc264af0f8477ff69f4872107cbe3567a6ffb64ac00190bf727d3d480c"},"schema_version":"1.0","source":{"id":"2110.04627","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04627","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04627v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04627","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"FMR6TAKPY4GK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FMR6TAKPY4GK7B2J","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FMR6TAKP","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e490304196f7f5212ad35a3b6733e12adadea75c1e84dda2c4a2a830ac10614d","target":"graph","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"When trained on ImageNet at 256×256 resolution, we achieve Inception Score (IS) of 175.1 and Fréchet Inception Distance (FID) of 4.17, a dramatic improvement over the vanilla VQGAN, which obtains 70.6 and 17.04 for IS and FID, respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the discrete tokens produced by the improved ViT-VQGAN retain enough visual information for autoregressive modeling to succeed at both high-quality generation and strong unsupervised representations without critical loss of detail or mode collapse."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An improved ViT-VQGAN produces discrete image tokens that let an autoregressive Transformer reach an Inception Score of 175.1 and FID of 4.17 on ImageNet."}],"snapshot_sha256":"b4daf46dd03dca15b66d07073bf100f3c56513e2ce4f99fd67b364bc3e1ab25b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0eec636ccc08a7e63b3e7b5fb0dd1306cee67f0d27686e029740c6322eb95b4e"},"paper":{"abstract_excerpt":"Pretraining language models with next-token prediction on massive text corpora has delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both generative and discriminative language tasks. Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively. The discrete image tokens are encoded from a learned Vision-Transformer-based VQGAN (ViT-VQGAN). We first propose multiple improvements over vanilla VQGAN from architecture to codebook learnin","authors_text":"Alexander Ku, Han Zhang, James Qin, Jason Baldridge, Jiahui Yu, Jing Yu Koh, Ruoming Pang, Xin Li, Yonghui Wu, Yuanzhong Xu","cross_cats":["cs.LG"],"headline":"An improved ViT-VQGAN produces discrete image tokens that let an autoregressive Transformer reach an Inception Score of 175.1 and FID of 4.17 on ImageNet.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-09T18:36:00Z","title":"Vector-quantized Image Modeling with Improved VQGAN"},"references":{"count":75,"internal_anchors":14,"resolved_work":75,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Schwing, Jan Kautz, and Arash Vahdat","work_id":"0fe7dc60-401a-4c98-a434-f44dc197d8f0","year":2010},{"cited_arxiv_id":"1906.00910","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Learning representations by maximizing mutual information across views","work_id":"65bca3d5-78f4-42d4-a6b1-cec1b702a646","year":1906},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Towards causal benchmarking of bias in face analysis algorithms, 2020","work_id":"6501ce5d-4889-498d-9bfe-6701c3b26b5b","year":2020},{"cited_arxiv_id":"2106.08254","doi":"","is_internal_anchor":true,"ref_index":4,"title":"BEiT: BERT Pre-Training of Image Transformers","work_id":"d74eda3c-bf7e-45f1-a8f1-a0137ecca3f4","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Large scale gan training for high fidelity natural image synthesis","work_id":"c8a7029d-c609-4cc5-8c21-654c100ca506","year":2019}],"snapshot_sha256":"35425ef17774a3871e1cc345ffc0fd40dfeb6c986012deae26f725c5ac88b615"},"source":{"id":"2110.04627","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T18:36:26.666226Z","id":"68ed06e5-14f0-41ec-ba4d-07d5e8bc5c83","model_set":{"reader":"grok-4.3"},"one_line_summary":"Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"An improved ViT-VQGAN produces discrete image tokens that let an autoregressive Transformer reach an Inception Score of 175.1 and FID of 4.17 on ImageNet.","strongest_claim":"When trained on ImageNet at 256×256 resolution, we achieve Inception Score (IS) of 175.1 and Fréchet Inception Distance (FID) of 4.17, a dramatic improvement over the vanilla VQGAN, which obtains 70.6 and 17.04 for IS and FID, respectively.","weakest_assumption":"That the discrete tokens produced by the improved ViT-VQGAN retain enough visual information for autoregressive modeling to succeed at both high-quality generation and strong unsupervised representations without critical loss of detail or mode collapse."}},"verdict_id":"68ed06e5-14f0-41ec-ba4d-07d5e8bc5c83"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c7e05c11cb65642eea53d4c7eec2fc421bd37c71f01913ae581d68be3327684b","target":"record","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1281174dc868bc9ba29a7618a8026ba8d4e9294520a78257df36a7f3417a8909","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-09T18:36:00Z","title_canon_sha256":"a7b3bfcc264af0f8477ff69f4872107cbe3567a6ffb64ac00190bf727d3d480c"},"schema_version":"1.0","source":{"id":"2110.04627","kind":"arxiv","version":3}},"canonical_sha256":"2b23e9814fc70caf8749f3c8d3812bfb427c20561b0eb78e59e0f5adcfb00686","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b23e9814fc70caf8749f3c8d3812bfb427c20561b0eb78e59e0f5adcfb00686","first_computed_at":"2026-05-17T23:38:46.953044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.953044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3v/dICYmc+w1JF4DUHwwfybQw4G3iJkbUnOd6djYbfNMvhtQtP6pJjrs1wRO+hBEWqijG4GR8yj1tBDBQMeMDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.953492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04627","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7e05c11cb65642eea53d4c7eec2fc421bd37c71f01913ae581d68be3327684b","sha256:e490304196f7f5212ad35a3b6733e12adadea75c1e84dda2c4a2a830ac10614d"],"state_sha256":"2e1eb1074304dbcf8037cbeee32841212652e27a66d8155114e21ccea95b5a5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WLmeD/IhBig8yjQAQAXZZg+8nbOUoaw8+GcfS+O3euPY9/GcKh0Z0FW6voqzanN+2AKQmDZpGGp/cDNyljDcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T05:09:59.766661Z","bundle_sha256":"187360e06fbccfafc53310bed63b1a8bb753b4dea8b5e121f2fe2a1e7d346baf"}}